High-Precision Positioning and Rotation Angle Estimation for a Target Pallet Based on BeiDou Navigation Satellite System and Vision.

In outdoor unmanned forklift unloading scenarios, pallet detection and localization face challenges posed by uncontrollable lighting conditions. Furthermore, the stacking and close arrangement of pallets also increase the difficulty of positioning a target pallet. To solve these problems, a method for high-precision positioning and rotation angle estimation for a target pallet using the BeiDou Navigation Satellite System (BDS) and vision is proposed. Deep dual-resolution networks (DDRNets) are used to segment the pallet from depth images and RGB images. Then, keypoints for calculating the position and rotation angle are extracted and further combined with the 3D point cloud data to achieve accurate pallet positioning. Constraining the pixel coordinates and depth coordinates of the center point of the pallet and setting the priority of the pallet according to the unloading direction allow the target pallet to be identified from multiple pallets. The positioning of the target pallet in the forklift navigation coordinate system is achieved by integrating BDS positioning data through coordinate transformation. This method is robust in response to lighting influences and can accurately locate the target pallet. The experimental results show that the pallet positioning error is less than 20 mm, and the rotation angle error is less than 0.37°, which meets the accuracy requirements for automated forklift operations.

High Precision Positioning and Rotation Angle Estimation of a Flatbed Truck Based on BDS and Vision.

Centimeter-level localization and precise rotation angle estimation for flatbed trucks pose significant challenges in unmanned forklift automated loading scenarios. To address this issue, the study proposed a method for high-precision positioning and rotation angle estimation of flatbed trucks using the BeiDou Navigation Satellite System (BDS) and vision technology. First, an unmanned forklift equipped with a Time-of-Flight (ToF) camera and a dual-antenna mobile receiver for BDS positioning collected depth images and localization data near the front and rear endpoints of the flatbed. The Deep Dual-Resolution Network-23-slim (DDRNet-23-slim) model was used to segment the flatbed from the depth image and extract the straight lines at the edges of the flatbed using the Hough transform. The algorithm then computed the set of intersection points of the lines. A neighborhood feature vector was designed to identify the endpoint of a flatbed from a set of intersection points using feature screening. Finally, the relative coordinates of the endpoints were converted to a customized forklift navigation coordinate system by BDS positioning. A rotation angle estimation was then performed using the endpoints at the front and rear. Experiments showed that the endpoint positioning error was less than 3 cm, and the rotation angle estimation error was less than 0.3°, which verified the validity and reliability of the method.

Automatic Lumbar Spine Tracking Based on Siamese Convolutional Network.

Deep learning has demonstrated great success in various computer vision tasks. However, tracking the lumbar spine by digitalized video fluoroscopic imaging (DVFI), which can quantitatively analyze the motion mode of the spine to diagnose lumbar instability, has not yet been well developed due to the lack of steady and robust tracking method. The aim of this work is to automatically track lumbar vertebras with rotated bounding boxes in DVFI sequences. Instead of distinguishing vertebras using annotated lumbar images or sequences, we train a full-convolutional siamese neural network offline to learn generic image features with transfer learning. The siamese network is trained to learn a similarity function that compares the labeled target from the initial frame with the candidate patches from the current frame. The similarity function returns a high score if the two images depict the same object. Once learned, the similarity function is used to track a previously unseen object without any adapting online. Our tracker is performed by evaluating the candidate rotated patches sampled around the previous target's position and presents rotated bounding boxes to locate the lumbar spine from L1 to L4. Results indicate that the proposed tracking method can track the lumbar vertebra steadily and robustly. The study demonstrates that the lumbar tracker based on siamese convolutional network can be trained successfully without annotated lumbar sequences.

Three-Dimensional ISAR Imaging Method for High-Speed Targets in Short-Range Using Impulse Radar Based on SIMO Array.

This paper proposes a three-dimensional inverse synthetic aperture radar (ISAR) imaging method for high-speed targets in short-range using an impulse radar. According to the requirements for high-speed target measurement in short-range, this paper establishes the single-input multiple-output (SIMO) antenna array, and further proposes a missile motion parameter estimation method based on impulse radar. By analyzing the motion geometry relationship of the warhead scattering center after translational compensation, this paper derives the receiving antenna position and the time delay after translational compensation, and thus overcomes the shortcomings of conventional translational compensation methods. By analyzing the motion characteristics of the missile, this paper estimates the missile's rotation angle and the rotation matrix by establishing a new coordinate system. Simulation results validate the performance of the proposed algorithm.